Taeyoung Kim
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Taeyoung Kim has a total of 2 co-authors. Here are the top co-authors by number of shared publications:
- Hyungbin Park
Research Institute of Mathematics, Seoul National University
1 shared publication - Wonjae Lee
Department of Mathematical Sciences, Seoul National University, Seoul, South Korea
1 shared publication
Latest Publications
- 6 April 2026
- Published by Springer Nature in Journal of Scientific Computing
- Vol. 107 (2) , 65
Fourier Neural Operators for Non-Markovian Processes: Approximation Theorems and Experiments
- 6 April 2026
- Published by Springer Nature in Journal of Scientific Computing
- Vol. 107 (2) , 65
Fourier Neural Operators for Non-Markovian Processes: Approximation Theorems and Experiments
- Open Access
- 20 March 2026
- Published by IOP Publishing in Machine Learning: Science and Technology
- Vol. 7 (2) , 025028
Analysis of Fourier neural operators via effective field theory
Fourier neural operators (FNOs) have emerged as leading surrogates for solver operators for various functional problems, yet their stability, generalization and frequency behavior lack a principled explanation. We present a systematic effective field theory analysis of FNOs in an infinite-dimensional function space, deriving closed recursion relations for the layer kernel and four-point vertex and then examining three practically important settings-analytic activations, scale-invariant cases and architectures with residual connections. The theory shows that nonlinear activations inevitably couple frequency inputs to high frequency modes that are otherwise discarded by spectral truncation, and experiments confirm this frequency transfer. For wide networks, we derive explicit criticality conditions on the weight initialization ensemble that ensure small input perturbations maintain a uniform scale across depth, and we confirm experimentally that the theoretically predicted ratio of kernel perturbations matches the measurements. Taken together, our results quantify how nonlinearity enables neural operators to capture non-trivial features, supply criteria for hyperparameter selection via criticality analysis, and explain why scale-invariant activations and residual connections enhance feature learning in FNOs. Finally, we translate the criticality theory into a practical criterion-matched initialization (calibration) procedure; on a standard PDEBench Burgers benchmark, the calibrated FNO exhibits markedly more stable optimization, faster convergence, and improved test error relative to a vanilla FNO.
- 20 March 2026
- Published by IOP Publishing in Machine Learning: Science and Technology
- Vol. 7 (2) , 025028
Open AccessAnalysis of Fourier neural operators via effective field theory
Fourier neural operators (FNOs) have emerged as leading surrogates for solver operators for various functional problems, yet their stability, generalization and frequency behavior lack a principled explanation. We present a systematic effective field theory analysis of FNOs in an infinite-dimensional function space, deriving closed recursion relations for the layer kernel and four-point vertex and then examining three practically important settings-analytic activations, scale-invariant cases and architectures with residual connections. The theory shows that nonlinear activations inevitably couple frequency inputs to high frequency modes that are otherwise discarded by spectral truncation, and experiments confirm this frequency transfer. For wide networks, we derive explicit criticality conditions on the weight initialization ensemble that ensure small input perturbations maintain a uniform scale across depth, and we confirm experimentally that the theoretically predicted ratio of kernel perturbations matches the measurements. Taken together, our results quantify how nonlinearity enables neural operators to capture non-trivial features, supply criteria for hyperparameter selection via criticality analysis, and explain why scale-invariant activations and residual connections enhance feature learning in FNOs. Finally, we translate the criticality theory into a practical criterion-matched initialization (calibration) procedure; on a standard PDEBench Burgers benchmark, the calibrated FNO exhibits markedly more stable optimization, faster convergence, and improved test error relative to a vanilla FNO.